Over the last few years, technological developments in semi-autonomous machines have raised awareness about the strategic importance of human-robot interaction (HRI) and its technical and social implications. At the same time, HRI still lacks an established pedagogic tradition in the coordination of its intrinsically interdisciplinary nature. This scenario presents steep and urgent challenges for HRI education. Our contribution presents a normative interdisciplinary dialogic framework for HRI education, denoted InDia wheel, aimed toward seamless and coherent integration of the variety of disciplines that contribute to HRI. Our framework deemphasizes technical mastery, reducing it to a necessary yet not sufficient condition for HRI design, thus modifying the stereotypical narration of HRI-relevant disciplines and creating favorable conditions for a more diverse participation of students. Prospectively, we argue, the design of an educational 'space of interaction’ that focuses on a variety of voices, without giving supremacy to one over the other, will be key to successful HRI education and practice.

The present workshop focuses on the topic of intention recognition in HRI. To be able to recognise intentions of other agents is a fundamental prerequisite to engage in, for instance, instrumental helping or mutual collaboration. It is a necessary aspect of natural interaction. In HRI, the problem is therefore bi-directional: not only does a robot need the ability to infer intentions of humans; humans also need to infer the intentions of the robot. From the human perspective, this inference draws both on the ability to attribute cognitive states to lifeless shapes, and the ability to understand actions of other agents through, for instance, embodied processes or internal simulations (i.e the human ability to form a theory of mind of other agents). How precisely, and to what degree these mechanisms are at work when interacting with social artificial agents remains unknown. From the robotic perspective, this lack of understanding of mechanisms underlying human intention recognition, or the capacity for theory of mind in general, is also challenging: the solution can, for instance, not simply be to make autonomous systems work “just like” humans by copying the biological solution and implementing some technological equivalent. It is therefore important to be clear about the theoretical framework(s) and inherent assumptions underlying technological implementations related to mutual intention. This remains very much an active research area in which further development is necessary. The core purpose of this workshop is thus to contribute to - and advance the state of the art in - this area.

Kinesthetic teaching is an established method of teaching robots new skills without requiring robotics or programming knowledge. However, the inertia and uncoordinated motions of individual joints decrease the intuitiveness and naturalness of interaction and impair the quality of the learned skill. This paper proposes a method to ease kinesthetic teaching by combining the idea of incremental learning through warping several demonstrations into a common frame with virtual tool dynamics to assist the user during teaching. In fact, during a sequence of demonstrations the stiffness of the robot under Cartesian impedance control is gradually increased, to provide stronger assistance to the user based on the demonstrations accumulated up to that moment. Therefore, the operator has the opportunity to progressively refine the task's model while the robot more docilely follows the learned action. Robot experiments and a user study performed on 25 novice users show that the proposed approach improves both usability as well as resulting skill quality.

Imitation learning of tasks in multi-component robotic systems requires capturing concurrency and synchronization requirements in addition to task structure. Learning time-critical tasks depends furthermore on the ability to model temporal elements in demonstrations. This paper proposes a modeling framework based on Petri nets capable of modeling these aspects in a programming by demonstration context. In the proposed approach, models of tasks are constructed from segmented demonstrations as task Petri nets, which can be executed as discrete controllers for reproduction. We present algorithms that automatically construct models from demonstrations, showing how elements of time-critical tasks can be mapped into task Petri net elements. The approach is validated by an experiment in which a robot plays a musical passage on a keyboard.

Learning to perform tasks like pulling a door handle or pushing a button, inherently easy for a human, can be surprisingly difficult for a robot. A crucial problem in these kinds of in-contact tasks is the context specificity of pose and force requirements. In this paper, a robot learns in-contact tasks from human kinesthetic demonstrations. To address the need to balance between the position and force constraints, we propose a model based on the hidden semi-Markov model (HSMM) and Cartesian impedance control. The model captures uncertainty over time and space and allows the robot to smoothly satisfy a task's position and force constraints by online modulation of impedance controller stiffness according to the HSMM state belief. In experiments, a KUKA LWR 4+ robotic arm equipped with a force/torque sensor at the wrist successfully learns from human demonstrations how to pull a door handle and push a button.

We present a (generalizable) method aimed to simultaneously transfer positional and force requirements encoded in a physical human skill (wood planing) from a human instructor to a robotic arm through kinesthetic teaching. We achieve our goal through a novel use of a common sensory configuration, constituted by a force/torque sensor mounted between the tool and the flange of a robotic arm. The robotic arm is endowed with integrated torque sensors at each joint. The mathematical model used to capture the general dynamic of the interaction between the human user and the wood surface is based on Dynamic Movement Primitives. During reenactment of the task, the system can imitate and generalize the demonstrated spatial requirements, as well as their associated force profiles. Therefore, the robotic arm acquires the capacity to reproduce the dynamic profile for in-contact tasks requiring an articulated coordination in the distribution of forces. For example, the capacity to effectively operate the plane on a wood plank over multiple strokes, according to the demonstration of the human instructor.